A Hybrid Reinforcement Learning BRKGA with Local Branching for a Sensor Allocation Problem

This study presents a novel approach to a Sensor Allocation Problem (SAP) in Wireless Sensor Networks (WSNs), a combinatorial optimization problem focused on optimizing network topology to minimize energy consumption while ensuring connectivity. We propose a hybrid methodology that combines the Biased Random-Key Genetic Algorithm (BRKGA), with reinforcement learning-based refinement incorporated into its decoder, and Local Branching techniques for efficient sensor placement. The integration of these techniques offers a scalable and adaptable solution to complex network configurations, achieving superior performance compared to traditional exact methods. Extensive computational experiments demonstrate the robustness and effectiveness of this approach across various network topologies, including regular, semi-regular networks. Our results highlight the ability of the proposed methodology to efficiently allocate sensors in large-scale, sparse, and dynamically changing networks, addressing the challenges of energy efficiency, connectivity, and coverage.